시맨틱 구문 트리 커널을 이용한 생명공학 분야 전문용어간 관계 식별 및 분류 연구 (A Study on the Identification and Classification of Relation Between Biotechnology Terms Using Semantic Parse Tree Kernel)

최성필 (Sung-Pil Choi); 정창후 (Chang-Hoo Jeong); 전홍우 (Hong-Woo Chun); 조현양 (Hyun Yang Cho)

doi:10.4275/KSLIS.2011.45.2.251

A Study on the Identification and Classification of Relation Between Biotechnology Terms Using Semantic Parse Tree Kernel

Journal of the Korean Society for Library and Information Science
2011, 45(2), pp.251-275
DOI : 10.4275/KSLIS.2011.45.2.251
Publisher : 한국문헌정보학회
Research Area : Interdisciplinary Studies > Library and Information Science
Received : April 13, 2011
Accepted : May 13, 2011

Sung-Pil Choi ¹, Chang-Hoo Jeong ¹, Hong-Woo Chun ¹, Hyun Yang Cho ²

¹한국과학기술정보연구원
²경기대학교

Accredited

ABSTRACT

In this paper, we propose a novel kernel called a semantic parse tree kernel that extends the parse tree kernel previously studied to extract protein-protein interactions(PPIs) and shown prominent results. Among the drawbacks of the existing parse tree kernel is that it could degenerate the overall performance of PPI extraction because the kernel function may produce lower kernel values of two sentences than the actual analogy between them due to the simple comparison mechanisms handling only the superficial aspects of the constituting words. The new kernel can compute the lexical semantic similarity as well as the syntactic analogy between two parse trees of target sentences. In order to calculate the lexical semantic similarity, it incorporates context-based word sense disambiguation producing synsets in WordNet as its outputs, which, in turn, can be transformed into more general ones. In experiments, we introduced two new parameters: tree kernel decay factors, and degrees of abstracting lexical concepts which can accelerate the optimization of PPI extraction performance in addition to the conventional SVM's regularization factor. Through these multi-strategic experiments, we confirmed the pivotal role of the newly applied parameters. Additionally, the experimental results showed that semantic parse tree kernel is superior to the conventional kernels especially in the PPI classification tasks.

KEYWORDS

Relation Extraction, Kernel-based Approaches, Parse Tree Kernels, Semantic Parse Tree Kernels, Word Sense Disambiguation

Citation status

* References for papers published after 2023 are currently being built.

[journal] Airola, A / 2008 / All-pathsgraph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning / BMC Bioinformatics 9(2)

[journal] Andrade, Miguel A / 1998 / Automatic extraction of keywords from scientifictext: Application to the knowledge domain of protein families / Bioinformatics 14(7) : 600~607

[confproc] Banerjee, S / 2002 / An adapted Lesk algorithm for word sense disambiguationusing WordNet / Proceedings of the 3rd International Conference on Intelligent Text Processingand Computational Linguistics(CICLing-2002) : 136~45

[confproc] Blaschke, C / 1999 / Automatic extraction ofbiological information from scientific text: Protein-protein interactions / Proceedings of theInternational Conference on Intelligent Systems for Molecular Biology : 60~67

[journal] Bunescu, R / 2005 / Comparative experiments on learning information extractors for proteins and their interactions / Artiicial Inteligence in Medicine, Summarization and Information Extraction from MedicalDocuments 33 : 139~155

[report] Collins, M / 2001 / Convolution kernels for natural language / NIPS

[confproc] Craven, M / 1999 / Constructing biological knowledge bases by extractinginformation from text sources / Proceedings of the 7th International Conference on IntelligentSystems for Molecular Biology : 77~86

[confproc] Ding, J / 2002 / Mining MEDLINE: abstracts,sentences, or phrases / Proceedings of PSB'02 : 326~337

[journal] Fundel, K / 2007 / RelEx - Relation extraction using dependencyparse trees / Bioinformatics 23 : 365~371

[journal] Gondy, L / 2003 / A shallow parser based on closed-classwords to capture relations in biomedical text / Journal of Biomedical Informatics 36(3) : 145~158

[confproc] Lesk,M / 1986 / Automatic sense disambiguation using machine readable dictionaries: Howto tell a pine cone from an ice cream cone / Proceedings of the 5th annual internationalconference on Systems documentation : 24~26

[journal] Marcotte / 2001 / Mining literature for protein-proteininteractions / Bioinformatics 17(4) : 359~363

[journal] Miwa, M / 2009 / Protein-protein interaction extractionby leveraging multiple kernels and parsers / International Journal of Medical Informatics

[confproc] Moschitti,A / 2006 / Making tree kernels practical for natural language learning / Proceedingsof EACL

[confproc] Nedellec,C / 2005 / Learning language in logic - genic interaction extraction challenge / Proceedingsof LLL'05 : 31~37

[journal] Nikolai, D / 2004 / Extractinghuman protein interactions from MEDLINE using a full-sentence parser / Bioinformatics 20(5) : 604~611

[journal] Ono, T / 2001 / Automated extraction of informationon protein-protein interactions from the biological literature / Bioinformatics 17(2) : 155~161

[journal] Pyysalo, S / 2008 / Comparativeanalysis of five protein-protein interaction corpora / BMC Bioinformatics 9(6)

[journal] Pyysalo, S / 2007 / BioInfer: A corpus for information extraction in the biomedical domain / BMC Bioinformatics 8(50)

[journal] Sekimizu, T / 1998 / Identifying the interaction between genes andgene products based on frequently seen verbs in MEDLINE abstracts / Workshop on genomeinformatics 9 : 62~71

[journal] Temkin, Joshua M / 2003 / Extraction of protein interaction informationfrom unstructured text using a context-free grammar / Bioinformatics 19(16) : 2046~2053

[confproc] Vishwanathan, S. V. N / 2003 / Fast kernels for string and tree matching / Processing Systems : 569~576

[web] Wikipedia / Wikipedia / http://en.wikipedia.org/wiki/Protein-protein_interaction

[confproc] Zhang, M / 2006 / A composite kernel to extract relationsbetween entities with both flat and structured features / 21st International Conference onComputational Linguistics and 44th Annual Meeting of the ACL : 825~832

[journal] Zhou, D. / 2008 / Extracting interactions between proteins from the literature / Journal of Biomedical Informatics 41 : 393~407

KJCKorea
Journal Central

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

A Study on the Identification and Classification of Relation Between Biotechnology Terms Using Semantic Parse Tree Kernel

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

A Study on the Identification and Classification of Relation Between Biotechnology Terms Using Semantic Parse Tree Kernel

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (3)

REFERENCES (25) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.